Overview
Gergay describes a sharp shift in software development toward AI-driven workflows. Based on visits and conversations with teams at OpenAI, Anthropic, Cursor, Ramp, Uber, Linear, and other companies, he argues that developers are moving away from writing code directly in IDEs and toward coordinating multiple coding agents through terminals, web tools, Slack, and internal platforms.
The change is not limited to code generation. Companies are rebuilding their development processes around agents that create tickets, open pull requests, assist with migrations, monitor production, and propose fixes.
Key Takeaways
AI-generated code is becoming the default at many startups that measure it. Engineers still direct, inspect, and edit the output, but Gergay says manually writing most code is increasingly rare.
Parallel work is replacing the old "one developer, one task" model. He cites engineers running five to ten worktrees or agent sessions at once, with agents handling separate tasks in parallel. The constraint is no longer keyboard time; it is the human ability to supply context, review work, and make decisions.
Traditional IDEs appear to be losing their central role. Gergay says agent-first interfaces such as Codex, Claude Code, Cursor's newer experience, and JetBrains Air are displacing heavyweight IDE workflows. Cursor reportedly described its IDE as a legacy product needed mainly for enterprise customers.
Internal AI coding platforms are becoming standard infrastructure. Companies including Ramp, Stripe, Uber, Shopify, Google, Meta, Amazon, DoorDash, and others have built internal agent harnesses. These systems connect models to private codebases, documentation, Slack, tickets, and operational data that companies may not want to expose to outside tools.
Development increasingly begins in collaboration tools. At OpenAI, Gergay says employees can tag Codex in Slack to request implementation work. Similar internal bots are appearing at Anthropic, Linear, and startups building their own integrations.
Large migrations that once took years can now move much faster. He points to Anthropic's Zig-to-Rust migration, OpenAI's reported Python-to-Rust API migration, and test-suite migrations at Airbnb, Asana, and Uber. AI reduces the repetitive work involved in broad codebase changes, though humans still need to control scope and review risk.
Agent-generated work is rising beyond code. Linear data reportedly shows more agent- or MCP-created issues than human-created issues on its platform. Gergay also points to growth in pull requests reviewed without a human, though he presents this as an emerging trend rather than a settled best practice.
Cost remains a constraint. As coding agents became more widely used, companies began worrying about spend, and Gergay cites reports that Uber exceeded its annual AI budget.
Practical Steps
Start with a small internal coding harness rather than waiting for a complete platform. Connect an approved model to your repository, issue tracker, documentation, and CI system. Keep permissions narrow at first.
Assign agents bounded tasks: test coverage, dependency upgrades, migrations, codebase discovery, documentation updates, or small bug fixes. Require pull requests and preserve human review for changes with a wide production impact.
Run work in parallel deliberately. Create separate worktrees or agent sessions for independent tasks, but give each agent clear context, acceptance criteria, and a defined owner.
Move repetitive migration work into an AI-assisted workflow. Break a migration into mechanical changes, validation steps, and rollback conditions. Let agents handle repeated edits while engineers focus on architecture and verification.
Track both output and cost. Measure accepted pull requests, review time, production incidents, model usage, and spend per task. More generated code is not useful if review capacity or infrastructure budgets become the bottleneck.
Notable Quotes
"It used to be a simple world: one mouse, one keyboard, one screen. You physically couldn't work on more things than one." - Dimas Tshekov, quoted by Gergay
"The developer work now often starts in Slack." - Gergay
"On the death of IDE, it's not that we don't need more perspective and context for human-based decisions. It's that the context has changed." - Kent Beck, quoted by Gergay
Full Transcript
Good morning. I'm Gergay, and thank you for the introduction. I now spend most of my time writing the pragmatic engineer, hosting the podcast, which is software engineering, big tech from the inside. And today I want to bring you into a journey, show you some stories, some information that might not be as readily available inside AI labs, big tech, and startups. In the last few months, I went inside the HQ of OpenAI and Tropic, Cursor, Ramp. I also talked with folks at Uber extensively, at Linear and other startups. Here's some of the the photos where I went, especially Ramp with the the office guy. And today, I want to cover first what changed, then what did not change, things that have broken across the industry, and what comes next. Let's start with what's changed, and a lot of things have changed. First thing, nobody writes code by hand anymore, except for a few of you folks. But in general, it's just more and more rare to see. Of course, we we still edit some code by hand, but it's crazy how much we are writing with AI. And this was kind of obvious to see in January. Like we we all woke up in January after the winter break, and we just saw that these models, starting from Opus 4.5 and GPT 5.2, were just really really good with the harnesses. And from there on, people switched. And in most startups that are tracking these numbers, it's gone to close to 100% AI generated code. That, of course, engineers prompt. Another thing that's changed: working with several agents, it's increasingly common. In March, I talk with Boris Cherny, who told me about how he has five terminal tabs, five Claude codes on his local machine, plus five to ten Clods on the web. Now, this is Boris Cherny. This is Entropic. Obviously, they will be, you know, cutting edge, and they will just honestly use AI. Sometimes, maybe even for the sake of AI. But I talked with Dimasatshev, who is an engineer, an old colleague of mine at Uber. He now works at Linear, and he put it really nicely. He said, "It used to be a simple world: one mouse, one keyboard, one screen. You physically couldn't work on more things than one. But we no longer have that limitation. So he's doing five to ten work trees. He's doing five to ten agents at the same time." And just the day before yesterday, I talked with Peter Mattis, co-founder CEO of Cockroach Labs. He's the person who built Gmail's first backend storage and a bunch of really cool storage stuff inside of Google. And he told me the same thing. Oftentimes, they're doing things in parallel. My cognitive overhead is five thousand agent sessions concurrently, and he just often does that as well. So again, so many people, so many kind of hardcore engineers, if you will, are have kind of moved to this mode of just parallel agents. It's pretty common. And I was talking with Ken Beck about this yesterday, and he texted me this. He said, "Like, hey, on the death of ID, it's not that we don't need more perspective and context for human-based decisions. It's that the context has changed. So maybe that's why it's going away." Everyone, and then some, are building their own harness and agent platform. And by everyone, I'm talking the start-ups, the big tech, the mid-sized companies. IDs are just fading away. This was really unexpected for me to see because I love my ID, but the trend of this heavy weight ID usage is trending down. People are using them just not as much. Anti-Gravity, released in November, the windsurf kind of rebrand, if you will, was the last major VS Code fork that was forked. And I talked with the OpenAI team just in June, and they told me that in January they were considering forking VS Code for the next version of Codex, but they were kind of torn in between: should we do it? Should we not? And for a little bit, they thought it was a mistake to build. Codex without an IDE, but they quickly realized actually they they did it the right time and and it was a win. JetBrains, one of the most beloved IDE brands, they're pivoting to Air, which is also more of an agentic harness, if you will. You can check out how it looks similar to Codex. Cursor, the biggest VS Code fork, has pivoted in April to just an agentic interface. Again, looks very similar to Codex. So all of these tools, and when I talk with the Cursor team inside of Cursor, they told me specifically that the IDE is now just a legacy product. They need it for enterprise, but it's not growing and it's shrinking. This used to be a buzzword that I used to be like agentic software. What like you know like like cars? Sure, one day, but no, it's actually happening. And one of the best examples is OpenAI's agentic software factory, which a deep dive is going out in a few hours. Into pragmatic engineers, so you'll be able to see, but. The developer work now often starts in Slack. So, inside OpenAI, they just tag Codex, implement this. Codex is plugged into all the OpenAI systems. On traffic, same thing with Claude. Right? They're part of the product as well. Startups increasingly build their own Slack agents and AI bot integrations. Linear does the same with their their linear bot and so on. The agentic software factory. I put this kind of tweet half jokingly saying, "If you're not built your AI coding harness, are you even a serious tech company?" And here are companies that built it: Ram, Stripe, Uber, Block, Shopify, Google, Meta, Amazon, Dropbox, Shopify, DoorDash, Grab, Worko, Asmundo, Hospital Sierra, Harvey's, Brewster, Base. So many more. Usually, they have cool internal names. By the way, it's really easy to do it as well, and they often do it so they can plug in their their data sources that they might not want to plug into Codex or or whatnot. And some of them are are building on top of Codex, Claude, Code, Open Code, and so on. But they're saying that it took about like four to five months to get here, under production load, nothing seen from the outside, and they're expecting to finish in a couple more months. And usually, we know these things would have taken years. So, but this is a great example because I don't just want to show the kind of days, which is a little bit like fairy tale stories. Airbnb moved up; they discontinued their enzyme. In this diagram that describes how their agentic sulfur factory works, those dashed lines, those dotted lines, are where agents act on typically agent input and they go back to Codex to generate a pull request. A human in the end often reviews a pull request for critical ones for large base radius. But OpenAI has this really cool concept of a perf factory run by agents which monitor production and raises PRs to improve production. And there just keep iterating on it. It's not fully automated and they don't have the goal, but it's happening. And this is a big change. Migration is no longer take years if we're paying attention. It's not as surprising, but some examples. Entropic migrated famously Zig to Rust with one engineer who wrote most of Bun, by the way. So this was really fast, and it probably would have taken years, and it probably just wouldn't have been done just because how when you migrate you need to maintain another thing. OpenAI, as I'll describe in a deep dive, this is new information that I got from them. They are migrating their API that hits all of their interfaces from Python to Rust. They are about ninety percent done, which is kind of what everyone says, by the way. So. UI testing library and went to React testing library. They migrated in six weeks and did a really nice write-up about how they did it. AI assisted. Asana did the same thing in about two weeks. There's some nuance there because they they spent a few years before doing it. And again, these are. These are practically full rewrites of test suites. It's not a replacing a library. There are some interesting details there. Uber moved from JUnit four to five in four months, in which those millions of lines of code. And again, it literally would have taken them just years clogging away beforehand. So these things are just cheaper and better and easier. Agentic generated issues are on the the rise. Fresh data from Linear shows that on their platform, the white line is human created issues tickets, and the blue line is agentic or MCP created tickets. And for the first time, more agentic created tickets are happening on their platform than human created ones. That's really, and you can see the sharp rise in the last few months. We're also seeing this is about agentic, agent-only pull requests are on the rise. So just in July and August, agentic pull requests are spiking. Sorry, agent-only reviewed pull requests where no human reviews it, which is also very interesting trend. Cost is is a big concern for a lot of you. Like you all know this, but back in back in May, there was already a widespread trend about companies worried about cost. This was around when it was made. It news that Uber blew through its its annual budget for AI, and cloth code was was becoming more popular. AI was getting more expensive.